A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition

TL;DR

This paper introduces a bi-directional multi-hop inference model that jointly improves dialog sentiment classification and act recognition by explicitly modeling their correlations and iteratively extracting rich contextual clues, leading to better accuracy and interpretability.

Contribution

The paper proposes a novel bi-directional multi-hop inference model with feature selection and contrastive learning for joint dialog sentiment and act recognition, outperforming existing methods.

Findings

Achieves at least 2.6% higher F1 in act recognition

Achieves at least 1.4% higher F1 in sentiment classification

Enhances interpretability of joint predictions

Abstract

The joint task of Dialog Sentiment Classification (DSC) and Act Recognition (DAR) aims to predict the sentiment label and act label for each utterance in a dialog simultaneously. However, current methods encode the dialog context in only one direction, which limits their ability to thoroughly comprehend the context. Moreover, these methods overlook the explicit correlations between sentiment and act labels, which leads to an insufficient ability to capture rich sentiment and act clues and hinders effective and accurate reasoning. To address these issues, we propose a Bi-directional Multi-hop Inference Model (BMIM) that leverages a feature selection network and a bi-directional multi-hop inference network to iteratively extract and integrate rich sentiment and act clues in a bi-directional manner. We also employ contrastive learning and dual learning to explicitly model the correlations of sentiment and act labels. Our experiments on two widely-used datasets show that BMIM outperforms state-of-the-art baselines by at least 2.6% on F1 score in DAR and 1.4% on F1 score in DSC. Additionally, Our proposed model not only improves the performance but also enhances the interpretability of the joint sentiment and act prediction task.